Big and Little Core Interrupt Scheduling Policy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional multi-core processors with identical cores fail to optimize battery life in mobile devices, as they equally manage power and performance across all cores, leading to inefficient use of smaller, more energy-efficient cores.
Innovation Solution
Implementing a scheduling policy that directs interrupts and tasks to either larger or smaller cores based on their processing needs, using predictive learning and core signatures to maximize the use of smaller cores and minimize the use of larger cores for power conservation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by moving object
If conventional multi-core processors with identical cores are used, then processing power is maintained, but battery life is not optimized and power consumption is inefficient
Solution Approach 1:
The processor is segmented into multiple cores of different sizes (big cores and little cores) with different performance characteristics. Big cores provide high processing power when needed, while little cores provide energy-efficient processing for less demanding tasks. This segmentation allows the system to optimize the balance between power consumption and processing power by assigning appropriate tasks to appropriate cores.
Solution Approach 2:
Different cores are assigned different qualities (performance levels) according to their characteristics. Big cores with higher performance are used for power-intensive tasks, while little cores with lower performance are used for energy-efficient tasks. This local differentiation of quality enables optimized power consumption without compromising overall system productivity.
2Use of energy by moving object
If smaller cores are used for all tasks, then power consumption is reduced, but processing capability for demanding tasks is insufficient
Solution Approach 1:
The system dynamically selects which cores to activate based on task requirements. For power-saving modes, the system can restrict execution to little cores only. For performance-critical tasks, the system activates big cores. This dynamic adaptation allows the system to optimize the balance between power consumption and processing capability according to real-time needs.
Solution Approach 2:
The system changes operational parameters by switching between different core configurations. When power consumption is the priority, the system configures the processor to use only little cores. When processing capability is the priority, the system configures the processor to use big cores. This parameter change enables flexible optimization of the power-performance trade-off.
3Power
If larger cores are used for all tasks, then processing capability is maximized, but battery life is reduced due to higher power consumption
Solution Approach 1:
The processor is divided into big cores and little cores, allowing the system to segment workloads appropriately. Less demanding tasks are executed on little cores to conserve battery life, while only necessary power-intensive tasks are executed on big cores. This segmentation extends battery life by minimizing the usage of high-power components.
Solution Approach 2:
The little cores act as energy-efficient, low-cost processing units for routine tasks. By using little cores for appropriate tasks, the system extends battery life without sacrificing necessary processing capability. The big cores serve as high-performance but power-intensive components that are used only when absolutely necessary.
4Productivity
If interrupts are not scheduled based on core size, then system simplicity is maintained, but task distribution efficiency is reduced
Solution Approach 1:
The scheduling system automatically directs interrupts and tasks to appropriate cores based on their characteristics without requiring manual intervention. The system self-manages task distribution by evaluating task requirements and assigning them to the most suitable core, thereby improving task distribution efficiency while keeping the complexity manageable through automated decision-making.
Data Source
AI summary
One aspect provides a method comprising: ascertaining an interrupt at an information handling device having two or more cores of different size; determining if the interrupt should be directed to one of a bigger core and a littler core based on a policy for scheduling interrupts; directing the interrupt to the little core if the interrupt does not qualify as an exception based on the policy for scheduling interrupts; and processing the interrupt on an appropriate core according the policy for scheduling interrupts. Other aspects are described and claimed.